{"id":7081,"date":"2025-07-15T05:48:00","date_gmt":"2025-07-14T20:48:00","guid":{"rendered":"https:\/\/devneko.jp\/wordpress\/?p=7081"},"modified":"2025-07-12T14:55:00","modified_gmt":"2025-07-12T05:55:00","slug":"gta1-gui-test-time-scaling-agent","status":"publish","type":"post","link":"https:\/\/devneko.jp\/wordpress\/?p=7081","title":{"rendered":"GTA1: GUI Test-time Scaling Agent\u00a0"},"content":{"rendered":"\n<ul class=\"wp-block-list\">\n<li><strong>GTA1: GUI Test-time Scaling Agent\u00a0<\/strong>[77.6]<br>\u672c\u7a3f\u3067\u306fGUI\u30c6\u30b9\u30c8\u30bf\u30a4\u30e0\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8GTA1\u306e2\u3064\u306e\u8ab2\u984c\u306b\u3064\u3044\u3066\u691c\u8a0e\u3059\u308b\u3002 \u307e\u305a\u3001\u6700\u3082\u9069\u5207\u306a\u30a2\u30af\u30b7\u30e7\u30f3\u63d0\u6848\u3092\u9078\u629e\u3059\u308b\u305f\u3081\u306b\u3001\u30c6\u30b9\u30c8\u6642\u9593\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u624b\u6cd5\u3092\u63d0\u6848\u3059\u308b\u3002 \u7b2c2\u306b\u3001\u9078\u629e\u3057\u305f\u30a2\u30af\u30b7\u30e7\u30f3\u63d0\u6848\u3092\u5bfe\u5fdc\u3059\u308b\u8996\u899a\u8981\u7d20\u306b\u30b0\u30e9\u30a6\u30f3\u30c9\u3059\u308b\u969b\u306e\u7cbe\u5ea6\u306e\u5411\u4e0a\u3092\u5b9f\u73fe\u3059\u308b\u30e2\u30c7\u30eb\u3092\u63d0\u6848\u3059\u308b\u3002<br><a href=\"http:\/\/arxiv.org\/abs\/2507.05791v1\">\u8ad6\u6587<\/a>\u00a0\u00a0<a href=\"https:\/\/fugumt.com\/fugumt\/paper_check\/2507.05791v1\">\u53c2\u8003\u8a33\uff08\u30e1\u30bf\u30c7\u30fc\u30bf\uff09<\/a>\u00a0 \u00a0(Tue, 08 Jul 2025 08:52:18 GMT)<\/li>\n\n\n\n<li>Salesforce research\u306b\u3088\u308bGUI\u30a8\u30fc\u30b8\u30a7\u30f3\u30c8\u306e\u63d0\u6848\u3001OSWorld\u306a\u3069\u3067SoTA\u3092\u4e3b\u5f35<\/li>\n\n\n\n<li>\u300ci) test-time scaling for planning, which introduces a scaling strategy during inference to effectively handle planning ambiguity in complex GUI environments; ii) grounding model training, filtering out training samples with annotation errors to improve supervision quality, and optimizing a grounding model using RL (e g , GRPO) to directly predict coordinates without relying on any intermediate \u201cthinking\u201d (i. e., CoT reasoning) on the derived data.\u300d\u3068\u3044\u3046\u5de5\u592b\u3092\u884c\u3063\u3066\u3044\u308b\u3002UI-TARS-1.5-7B, Qwen2.5-VL-32B-Instruct, Qwen2.5-VL-72B-Instruct\u3092Post Training\u3057\u3066\u3044\u308b\u304c\u3001\u3084\u306f\u308a\u3053\u306e\u624b\u306e\u30c1\u30e5\u30fc\u30cb\u30f3\u30b0\u3092\u884c\u308f\u306a\u3044\u3068\u53b3\u3057\u3044\u30bf\u30b9\u30af\u306a\u306e\u3060\u308d\u3046\u304b\u30fb\u30fb\u30fb<\/li>\n\n\n\n<li>\u30ea\u30dd\u30b8\u30c8\u30ea\u306f<a href=\"https:\/\/github.com\/Yan98\/GTA1\">GitHub &#8211; Yan98\/GTA1<\/a><\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[181],"class_list":["post-7081","post","type-post","status-publish","format-standard","hentry","category-arxiv","tag-gui-agent"],"_links":{"self":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7081","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=7081"}],"version-history":[{"count":1,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7081\/revisions"}],"predecessor-version":[{"id":7082,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=\/wp\/v2\/posts\/7081\/revisions\/7082"}],"wp:attachment":[{"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=7081"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=7081"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/devneko.jp\/wordpress\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=7081"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}